用智能代理动态调整聚类过程，让文本分类更灵活可控。
Agentic Clustering: Controllable Text Taxonomies via Multi-Agent Refinement
- 用多个专业代理（提议、合成、审计等）动态协作，自适应调整聚类流程。
- 在7个公开数据集上最高提升32%的ARI得分，达到当前最优性能。
- 适合需要指定聚类数量或意图的用户，可灵活应对不同文本结构。
现有文本聚类方法利用大语言模型从语料库中提出聚类分类体系，并分配每条文本。这些流程本质是程序化的：LLM调用顺序和停止、合并、拆分聚类的规则预先固定，导致在不同结构的语料上泛化能力差，且难以融入用户设定的约束（如目标聚类数或聚类意图）。我们提出一种代理式替代方案：由一个协调者LLM在每一步检查发现状态，并调度一组少量专业化代理——提议者、合成者、审计者、调查者和批评者——根据语料特点动态调整流程，而非执行固定管道。在七个公开文本聚类基准上，该方法取得当前最佳性能，相较于最强的先前LLM基线，最高提升32%的ARI得分。
原文摘要 · Abstract (English)
Recent text-clustering methods use large language models to propose a cluster taxonomy from a corpus and then assign each text to it. These pipelines are fundamentally programmatic: the sequence of LLM calls and the rules for stopping, merging, and splitting clusters are fixed in code in advance, so they generalise poorly across corpora of different structure and cannot easily incorporate user-supplied constraints such as a target cluster count or a clustering intent. We propose an agentic alternative in which an orchestrator LLM inspects the state of the discovery process at each step and dispatches one of a small set of specialised agents - proposer, synthesizer, auditor, investigator, and critic - adapting the pipeline to the corpus rather than executing a fixed one. On seven public text-clustering benchmarks the method achieves state-of-the-art performance, beating the strongest prior LLM baseline by up to 32% in ARI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。